sdd-spec
Skill10 starsChanged 20 days agoMITView on GitHub
Formal specification document authoring for spec-driven development
We split this skill into the rules it gives an agent
3 rules. 0 are common, 2 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 5 edited versions we read keep these.
2
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 9
Write a formal specification document that the Designer and Implementer will use as their source of truth.
- Very specific: line 22
Use "Given/When/Then" or precondition/action/postcondition format
- Distinctive: line 42
Specify non-functional requirements: Add constraints beyond behavior.
“Common” is measured: kept by at least 6 in 10 of the 5 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
SDD Spec Skill
Write a formal specification document that the Designer and Implementer will use as their source of truth. The spec must be complete enough that two different developers could implement the same behavior independently.
Steps
- State the problem: Define what problem is being solved.
- What user need or system requirement motivates this change?
- What is currently broken or missing?
- What is out of scope (explicit exclusions)?
- Define success criteria: List measurable acceptance tests.
- Each criterion must be testable (observable and verifiable)
- Use "Given/When/Then" or precondition/action/postcondition format
- Cover both functional and non-functional criteria
- Specify the interface contract: Define the public surface precisely.
- Function/method signatures with parameter and return types
- Error types and when they are returned
- Side effects (files created, state changed, events emitted)
- Invariants that must hold before and after each operation
- Specify data structures: Define all types involved.
- Fields, types, and optionality
- Validation rules (allowed values, format constraints)
- Serialization format (JSON schema, protobuf, etc.)
- Specify behavior for edge cases: Cover boundary conditions explicitly.
- What happens with empty input?
- What happens with maximum-size input?
- What happens if a dependency is unavailable?
- What partial failure behavior is acceptable?
- Specify non-functional requirements: Add constraints beyond behavior.
- Performance: maximum latency, throughput, memory usage
- Security: authentication, authorization, input sanitization
- Reliability: retry behavior, timeout, fallback
Output Format
## Specification: <feature name>
### Problem Statement
<1-3 sentences describing what problem this solves>
### Scope
**In scope**: <what this spec covers>
**Out of scope**: <explicit exclusions>
### Success Criteria
1. Given <precondition>, when <action>, then <expected outcome>
2. ...
### Interface Contract
#### <FunctionName>(params) (returnType, error)
- **Purpose**: <what it does>
- **Parameters**: <name type: description>
- **Returns**: <description of return value>
- **Errors**: <error type: when it is returned>
- **Side effects**: <what changes as a result>
- **Invariants**: <what must be true before/after>
### Data Structures
#### <TypeName>
| Field | Type | Required | Description |
|-------|------|----------|-------------|
### Edge Case Behavior
| Condition | Expected Behavior |
|-----------|------------------|
### Non-Functional Requirements
- **Performance**: <requirement>
- **Security**: <requirement>
- **Reliability**: <requirement>Other versions6 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 6
- felipefontoura/pi-sdd-kit★ 36same name
- khangpqvn/SDDADD★ 12same name
- ad1code/sdd-harness★ 4same name
- Maicololiveras/praxisgenai-agent-orchestrator★ 1same name
- svg153/skills★ 1same name
- callingcard1973/claude-skills★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository28 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- .github/copilot-instructions.mdCopilot instructions
- code-reviewSkill
- context-disciplineSkill
- find-skillsSkill
- pr-descriptionSkill
- sdd-applySkill
- sdd-designSkill
- sdd-exploreSkill
- sdd-proposeSkill
- sdd-tasksSkill
- sdd-verifySkill
- squadai-init-playbookSkill
- testingSkill
- code-reviewSkill
- context-disciplineSkill
- find-skillsSkill
- pr-descriptionSkill
- sdd-applySkill
- sdd-designSkill
- sdd-exploreSkill
- sdd-proposeSkill
- sdd-specSkill
- sdd-tasksSkill
- sdd-verifySkill
- squadai-init-playbookSkill
- testingSkill
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

